diff options
author | Campbell Barton <ideasman42@gmail.com> | 2011-10-20 13:47:05 +0400 |
---|---|---|
committer | Campbell Barton <ideasman42@gmail.com> | 2011-10-20 13:47:05 +0400 |
commit | 8d6a554d7502029f04aca33efcdd004744b9bd84 (patch) | |
tree | 027f5dec3ea38784d3108f8d9b5c4a008bae7fb4 /source/blender/blenkernel/intern/font.c | |
parent | e02dfe4a79b3632b3143d5d45e0dee1463ff7aa6 (diff) |
- add BLI_string_utf8.h for unicode functions.
- move font.c unicode functions into string_utf8.c and rename to fit with other BLI_string funcs.
Diffstat (limited to 'source/blender/blenkernel/intern/font.c')
-rw-r--r-- | source/blender/blenkernel/intern/font.c | 140 |
1 files changed, 2 insertions, 138 deletions
diff --git a/source/blender/blenkernel/intern/font.c b/source/blender/blenkernel/intern/font.c index 9c01b35b91a..068e70bbb50 100644 --- a/source/blender/blenkernel/intern/font.c +++ b/source/blender/blenkernel/intern/font.c @@ -64,142 +64,6 @@ static ListBase ttfdata= {NULL, NULL}; -/* UTF-8 <-> wchar transformations */ -size_t chtoutf8(const unsigned long c, char o[4]) -{ - // Variables and initialization -/* memset(o, 0, 4); */ - - // Create the utf-8 string - if (c < 0x80) { - o[0] = (char) c; - return 1; - } - else if (c < 0x800) { - o[0] = (0xC0 | (c>>6)); - o[1] = (0x80 | (c & 0x3f)); - return 2; - } - else if (c < 0x10000) { - o[0] = (0xe0 | (c >> 12)); - o[1] = (0x80 | (c >>6 & 0x3f)); - o[2] = (0x80 | (c & 0x3f)); - return 3; - } - else if (c < 0x200000) { - o[0] = (0xf0 | (c>>18)); - o[1] = (0x80 | (c >>12 & 0x3f)); - o[2] = (0x80 | (c >> 6 & 0x3f)); - o[3] = (0x80 | (c & 0x3f)); - return 4; - } - - /* should we assert here? */ - return 0; -} - -void wcs2utf8s(char *dst, const wchar_t *src) -{ - while(*src) { - dst += chtoutf8(*src++, dst); - } - - *dst= '\0'; -} - -size_t wcsleninu8(wchar_t *src) -{ - char ch_dummy[4]; - size_t len = 0; - - while(*src) { - len += chtoutf8(*src++, ch_dummy); - } - - return len; -} - -static size_t utf8slen(const char *strc) -{ - int len=0; - - while(*strc) { - if ((*strc & 0xe0) == 0xc0) { - if((strc[1] & 0x80) && (strc[1] & 0x40) == 0x00) - strc++; - } else if ((*strc & 0xf0) == 0xe0) { - if((strc[1] & strc[2] & 0x80) && ((strc[1] | strc[2]) & 0x40) == 0x00) - strc += 2; - } else if ((*strc & 0xf8) == 0xf0) { - if((strc[1] & strc[2] & strc[3] & 0x80) && ((strc[1] | strc[2] | strc[3]) & 0x40) == 0x00) - strc += 3; - } - - strc++; - len++; - } - - return len; -} - - -/* Converts Unicode to wchar - -According to RFC 3629 "UTF-8, a transformation format of ISO 10646" -(http://tools.ietf.org/html/rfc3629), the valid UTF-8 encoding are: - - Char. number range | UTF-8 octet sequence - (hexadecimal) | (binary) - --------------------+--------------------------------------------- - 0000 0000-0000 007F | 0xxxxxxx - 0000 0080-0000 07FF | 110xxxxx 10xxxxxx - 0000 0800-0000 FFFF | 1110xxxx 10xxxxxx 10xxxxxx - 0001 0000-0010 FFFF | 11110xxx 10xxxxxx 10xxxxxx 10xxxxxx - -If the encoding incidated by the first character is incorrect (because the -1 to 3 following characters do not match 10xxxxxx), the output is a '?' and -only a single input character is consumed. - -*/ - -size_t utf8towchar(wchar_t *w, const char *c) -{ - int len=0; - - if(w==NULL || c==NULL) return(0); - - while(*c) { - if ((*c & 0xe0) == 0xc0) { - if((c[1] & 0x80) && (c[1] & 0x40) == 0x00) { - *w=((c[0] &0x1f)<<6) | (c[1]&0x3f); - c++; - } else { - *w = '?'; - } - } else if ((*c & 0xf0) == 0xe0) { - if((c[1] & c[2] & 0x80) && ((c[1] | c[2]) & 0x40) == 0x00) { - *w=((c[0] & 0x0f)<<12) | ((c[1]&0x3f)<<6) | (c[2]&0x3f); - c += 2; - } else { - *w = '?'; - } - } else if ((*c & 0xf8) == 0xf0) { - if((c[1] & c[2] & c[3] & 0x80) && ((c[1] | c[2] | c[3]) & 0x40) == 0x00) { - *w=((c[0] & 0x07)<<18) | ((c[1]&0x1f)<<12) | ((c[2]&0x3f)<<6) | (c[3]&0x3f); - c += 3; - } else { - *w = '?'; - } - } else - *w=(c[0] & 0x7f); - - c++; - w++; - len++; - } - return len; -} - /* The vfont code */ void free_vfont(struct VFont *vf) { @@ -691,10 +555,10 @@ struct chartrans *BKE_text_to_curve(Main *bmain, Scene *scene, Object *ob, int m if(vfont == NULL) return NULL; // Create unicode string - utf8len = utf8slen(cu->str); + utf8len = BLI_strlen_utf8(cu->str); mem = MEM_callocN(((utf8len + 1) * sizeof(wchar_t)), "convertedmem"); - utf8towchar(mem, cu->str); + BLI_strncpy_wchar_from_utf8(mem, cu->str, utf8len + 1); // Count the wchar_t string length slen = wcslen(mem); |